WebScraping-AI MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEBSCRAPING_AI_API_KEY | Yes | Your WebScraping.AI API key, required for all operations | |
| WEBSCRAPING_AI_DEFAULT_TIMEOUT | No | Maximum web page retrieval time in ms (max: 30000) | 15000 |
| WEBSCRAPING_AI_CONCURRENCY_LIMIT | No | Maximum number of concurrent requests | 5 |
| WEBSCRAPING_AI_DEFAULT_JS_TIMEOUT | No | Maximum JavaScript rendering time in ms | 2000 |
| WEBSCRAPING_AI_DEFAULT_PROXY_TYPE | No | Type of proxy to use (datacenter or residential) | residential |
| WEBSCRAPING_AI_DEFAULT_JS_RENDERING | No | Enable/disable JavaScript rendering | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| webscraping_ai_questionD | – |
| webscraping_ai_fieldsD | – |
| webscraping_ai_htmlD | – |
| webscraping_ai_textD | – |
| webscraping_ai_selectedD | – |
| webscraping_ai_selected_multipleD | – |
| webscraping_ai_accountD | – |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
The names suggest distinct output modes, but several tools overlap conceptually (html vs. text vs. fields vs. question), and selected vs. selected_multiple could easily confuse an agent without descriptions. The lack of descriptions worsens this ambiguity.
All tools share the webscraping_ai_ prefix and snake_case convention, making the set look cohesive. The suffixes are mostly nouns/adjectives rather than verb_noun actions, but the pattern is predictable and consistent.
Seven tools is a reasonable size for a scraping-focused serverched. The count covers several output modes without feeling bloated, though selected and selected_multiple could arguably be one parameterized tool.
The domain is inferable from the names: HTML/text/field extraction, selected elements, and question-answering over scraped content. It lacks some common extras like link extraction or screenshot, but the core scraping workflow appears covered.